Adding Evaluation Results

README.md

@@ -1,9 +1,112 @@
 ---
-license: apache-2.0
 language:
 - en
+license: apache-2.0
 tags:
 - merge
+model-index:
+- name: v1olet_marcoroni-go-bruins-7B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 29.1
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=v1olet/v1olet_marcoroni-go-bruins-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 28.3
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=v1olet/v1olet_marcoroni-go-bruins-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 25.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=v1olet/v1olet_marcoroni-go-bruins-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 0.0
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=v1olet/v1olet_marcoroni-go-bruins-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 52.09
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=v1olet/v1olet_marcoroni-go-bruins-7B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 0.0
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=v1olet/v1olet_marcoroni-go-bruins-7B
+      name: Open LLM Leaderboard
 ---
 
 ### 12th December 2023
@@ -46,4 +149,17 @@ template_format = """{system}
 """
 ```
 
-Developed by: Trong-Hieu Nguyen-Mau
+Developed by: Trong-Hieu Nguyen-Mau
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_v1olet__v1olet_marcoroni-go-bruins-7B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |22.43|
+|AI2 Reasoning Challenge (25-Shot)|29.10|
+|HellaSwag (10-Shot)              |28.30|
+|MMLU (5-Shot)                    |25.09|
+|TruthfulQA (0-shot)              | 0.00|
+|Winogrande (5-shot)              |52.09|
+|GSM8k (5-shot)                   | 0.00|
+